Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tian
    -0.08
     humanities
    -0.07
    CoreApplication
    -0.07
     позитив
    -0.07
     ullam
    -0.07
     refill
    -0.06
     skirts
    -0.06
     zw
    -0.06
     gim
    -0.06
    カー
    -0.06
    POSITIVE LOGITS
    .handleError
    0.06
     Collapse
    0.06
    gradation
    0.06
    uby
    0.06
    opic
    0.06
    hist
    0.06
    edores
    0.06
    ілля
    0.06
     preprocess
    0.06
    /resources
    0.06
    Act Density 0.018%

    No Known Activations